# Research Papers — 2025-10 · bundle page 47 of 217

> Full-text markdown of papers #2301–2350 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/47
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/46.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/48.md)

### Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

Authors: Hoang Phan, Xianjun Yang, Yuanshun Yao, Jingyu Zhang, Shengjie Bi, Xiaocheng Tang, Madian Khabsa, Lijuan Liu, Deren Lei
Published: 2025-10-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.21978v2

Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models. However, the RLVR recipe introduces a significant risk of capability regression, in which models forget foundational skills after prolonged training without employing regularization strategies. We empirically confirm this concern, observing that open-source reasoning models suffer performance degradation on core capabilities such as perception and faithfulness. While imposing regularization terms like KL divergence can help prevent deviation from the base model, these terms are computed on the current task and therefore do not guarantee preservation of broader knowledge. Meanwhile, commonly used experience replay across heterogeneous domains makes it nontrivial to decide how much training emphasis each objective should receive. To address this, we propose RECAP-a replay strategy with dynamic objective reweighting for general knowledge preservation. Our reweighting mechanism adapts online using short-horizon signals of convergence and instability, shifting the post-training focus away from saturated objectives and toward underperforming or volatile ones. Our method is end-to-end and readily applicable to existing RLVR pipelines without training additional models or heavy tuning. Extensive experiments on benchmarks using Qwen2.5-VL-3B and Qwen2.5-VL-7B demonstrate the effectiveness of our method, which not only preserves general capabilities but also improves reasoning by enabling more flexible trade-offs among in-task rewards.

---

### Distribution Shift Alignment Helps LLMs Simulate Survey Response Distributions

Authors: Ji Huang, Mengfei Li, Shuai Shao
Published: 2025-10-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.21977v2

Large language models (LLMs) offer a promising way to simulate human survey responses, potentially reducing the cost of large-scale data collection. However, existing zero-shot methods suffer from prompt sensitivity and low accuracy, while conventional fine-tuning approaches mostly fit the training set distributions and struggle to produce results more accurate than the training set itself, which deviates from the original goal of using LLMs to simulate survey responses. Building on this observation, we introduce Distribution Shift Alignment (DSA), a two-stage fine-tuning method that aligns both the output distributions and the distribution shifts across different backgrounds. By learning how these distributions change rather than fitting training data, DSA can provide results substantially closer to the true distribution than the training data. Empirically, DSA consistently outperforms other methods on five public survey datasets. We further conduct a comprehensive comparison covering accuracy, robustness, and data savings. DSA reduces the required real data by 53.48-69.12%, demonstrating its effectiveness and efficiency in survey simulation.

---

### Deep Jump Gaussian Processes for Surrogate Modeling of High-Dimensional Piecewise Continuous Functions

Authors: Yang Xu, Chiwoo Park
Published: 2025-10-24
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.21974v3

We introduce Deep Jump Gaussian Processes (DJGP), a novel method for surrogate modeling of a piecewise continuous function on a high-dimensional domain. DJGP addresses the limitations of conventional Jump Gaussian Processes (JGP) in high-dimensional input spaces by integrating region-specific, locally linear projections with JGP modeling. These projections employ region-dependent matrices to capture local low-dimensional subspace structures, making them well suited to the inherently localized modeling behavior of JGPs, a variant of local Gaussian processes. To control model complexity, we place a Gaussian Process prior on the projection matrices, allowing them to evolve smoothly across the input space. The projected inputs are then modeled with a JGP to capture piecewise continuous relationships with the response. This yields a distinctive two-layer deep learning of GP/JGP. We further develop a scalable variational inference algorithm to jointly learn the projection matrices and JGP hyperparameters. Rigorous theoretical analysis and extensive empirical studies are provided to justify the proposed approach. In particular, we derive an oracle error bound for DJGP and decompose it into four distinct sources of error, which are then linked to practical implications. Experiments on synthetic and benchmark datasets demonstrate that DJGP achieves superior predictive accuracy and more reliable uncertainty quantification compared with existing methods.

---

### Performance Trade-offs of Optimizing Small Language Models for E-Commerce

Authors: Josip Tomo Licardo, Nikola Tankovic
Published: 2025-10-24
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.21970v1

Large Language Models (LLMs) offer state-of-the-art performance in natural language understanding and generation tasks. However, the deployment of leading commercial models for specialized tasks, such as e-commerce, is often hindered by high computational costs, latency, and operational expenses. This paper investigates the viability of smaller, open-weight models as a resource-efficient alternative. We present a methodology for optimizing a one-billion-parameter Llama 3.2 model for multilingual e-commerce intent recognition. The model was fine-tuned using Quantized Low-Rank Adaptation (QLoRA) on a synthetically generated dataset designed to mimic real-world user queries. Subsequently, we applied post-training quantization techniques, creating GPU-optimized (GPTQ) and CPU-optimized (GGUF) versions. Our results demonstrate that the specialized 1B model achieves 99% accuracy, matching the performance of the significantly larger GPT-4.1 model. A detailed performance analysis revealed critical, hardware-dependent trade-offs: while 4-bit GPTQ reduced VRAM usage by 41%, it paradoxically slowed inference by 82% on an older GPU architecture (NVIDIA T4) due to dequantization overhead. Conversely, GGUF formats on a CPU achieved a speedup of up to 18x in inference throughput and a reduction of over 90% in RAM consumption compared to the FP16 baseline. We conclude that small, properly optimized open-weight models are not just a viable but a more suitable alternative for domain-specific applications, offering state-of-the-art accuracy at a fraction of the computational cost.

---

### Adaptive Split-MMD Training for Small-Sample Cross-Dataset P300 EEG Classification

Authors: Weiyu Chen, Arnaud Delorme
Published: 2025-10-24
Categories: eess.SP, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2510.21969v1

Detecting single-trial P300 from EEG is difficult when only a few labeled trials are available. When attempting to boost a small target set with a large source dataset through transfer learning, cross-dataset shift arises. To address this challenge, we study transfer between two public visual-oddball ERP datasets using five shared electrodes (Fz, Pz, P3, P4, Oz) under a strict small-sample regime (target: 10 trials/subject; source: 80 trials/subject). We introduce Adaptive Split Maximum Mean Discrepancy Training (AS-MMD), which combines (i) a target-weighted loss with warm-up tied to the square root of the source/target size ratio, (ii) Split Batch Normalization (Split-BN) with shared affine parameters and per-domain running statistics, and (iii) a parameter-free logit-level Radial Basis Function kernel Maximum Mean Discrepancy (RBF-MMD) term using the median-bandwidth heuristic. Implemented on an EEG Conformer, AS-MMD is backbone-agnostic and leaves the inference-time model unchanged. Across both transfer directions, it outperforms target-only and pooled training (Active Visual Oddball: accuracy/AUC 0.66/0.74; ERP CORE P3: 0.61/0.65), with gains over pooling significant under corrected paired t-tests. Ablations attribute improvements to all three components.

---

### ArchISMiner: A Framework for Automatic Mining of Architectural Issue-Solution Pairs from Online Developer Communities

Authors: Musengamana Jean de Dieu, Ruiyin Li, Peng Liang, Mojtaba Shahin, Muhammad Waseem, Arif Ali Khan, Bangchao Wang, Mst Shamima Aktar
Published: 2025-10-24
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.21966v1

Stack Overflow (SO), a leading online community forum, is a rich source of software development knowledge. However, locating architectural knowledge, such as architectural solutions remains challenging due to the overwhelming volume of unstructured content and fragmented discussions. Developers must manually sift through posts to find relevant architectural insights, which is time-consuming and error-prone. This study introduces ArchISMiner, a framework for mining architectural knowledge from SO. The framework comprises two complementary components: ArchPI and ArchISPE. ArchPI trains and evaluates multiple models, including conventional ML/DL models, Pre-trained Language Models (PLMs), and Large Language Models (LLMs), and selects the best-performing model to automatically identify Architecture-Related Posts (ARPs) among programming-related discussions. ArchISPE employs an indirect supervised approach that leverages diverse features, including BERT embeddings and local TextCNN features, to extract architectural issue-solution pairs. Our evaluation shows that the best model in ArchPI achieves an F1-score of 0.960 in ARP detection, and ArchISPE outperforms baselines in both SE and NLP fields, achieving F1-scores of 0.883 for architectural issues and 0.894 for solutions. A user study further validated the quality (e.g., relevance and usefulness) of the identified ARPs and the extracted issue-solution pairs. Moreover, we applied ArchISMiner to three additional forums, releasing a dataset of over 18K architectural issue-solution pairs. Overall, ArchISMiner can help architects and developers identify ARPs and extract succinct, relevant, and useful architectural knowledge from developer communities more accurately and efficiently. The replication package of this study has been provided at https://github.com/JeanMusenga/ArchISPE

---

### Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing

Authors: Iskander Azangulov, Teodora Pandeva, Niranjani Prasad, Javier Zazo, Sushrut Karmalkar
Published: 2025-10-24
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.21961v1

Masked diffusion models (MDMs) offer a compelling alternative to autoregressive models (ARMs) for discrete text generation because they enable parallel token sampling, rather than sequential, left-to-right generation. This means potentially much faster inference. However, effective parallel sampling faces two competing requirements: (i) simultaneously updated tokens must be conditionally independent, and (ii) updates should prioritise high-confidence predictions. These goals conflict because high-confidence predictions often cluster and depend on each other, opportunities for parallel updates. We present PUNT, a model-agnostic sampler that reconciles this trade-off. Our method identifies token dependencies and removes lower-confidence tokens from conflicting groups. This produces sets of indices for unmasking that satisfy both independence and confidence criteria. Our approach ensures improved parallel unmasking through approximate conditional independence testing. Our experiments show that PUNT delivers a superior trade-off between accuracy and compute when compared to other strong training-free baselines, especially for generation of longer sequences. On the IFEval benchmark, it achieves up to 16\% higher accuracy over baseline methods, including sequential generation (one-by-one). These gains hold across different values of hyperparameters, mitigating the need for brittle hyperparameter tuning. Moreover, we observe that PUNT induces an emergent hierarchical generation strategy, where the model first establishes high-level paragraph structure before local refinement, suggesting a planning-like generation process that contributes to strong alignment performance.

---

### A Stylometric Application of Large Language Models

Authors: Harrison F. Stropkay, Jiayi Chen, Mohammad J. Latifi, Daniel N. Rockmore, Jeremy R. Manning
Published: 2025-10-24
Categories: cs.CL, cs.DL
arXiv: https://arxiv.org/abs/2510.21958v1

We show that large language models (LLMs) can be used to distinguish the writings of different authors. Specifically, an individual GPT-2 model, trained from scratch on the works of one author, will predict held-out text from that author more accurately than held-out text from other authors. We suggest that, in this way, a model trained on one author's works embodies the unique writing style of that author. We first demonstrate our approach on books written by eight different (known) authors. We also use this approach to confirm R. P. Thompson's authorship of the well-studied 15th book of the Oz series, originally attributed to F. L. Baum.

---

### Towards Low-Latency and Adaptive Ransomware Detection Using Contrastive Learning

Authors: Zhixin Pan, Ziyu Shu, Amberbir Alemayoh
Published: 2025-10-24
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.21957v1

Ransomware has become a critical threat to cybersecurity due to its rapid evolution, the necessity for early detection, and growing diversity, posing significant challenges to traditional detection methods. While AI-based approaches had been proposed by prior works to assist ransomware detection, existing methods suffer from three major limitations, ad-hoc feature dependencies, delayed response, and limited adaptability to unseen variants. In this paper, we propose a framework that integrates self-supervised contrastive learning with neural architecture search (NAS) to address these challenges. Specifically, this paper offers three important contributions. (1) We design a contrastive learning framework that incorporates hardware performance counters (HPC) to analyze the runtime behavior of target ransomware. (2) We introduce a customized loss function that encourages early-stage detection of malicious activity, and significantly reduces the detection latency. (3) We deploy a neural architecture search (NAS) framework to automatically construct adaptive model architectures, allowing the detector to flexibly align with unseen ransomware variants. Experimental results show that our proposed method achieves significant improvements in both detection accuracy (up to 16.1%) and response time (up to 6x) compared to existing approaches while maintaining robustness under evasive attacks.

---

### Transformer Based Linear Attention with Optimized GPU Kernel Implementation

Authors: Armin Gerami, Ramani Duraiswami
Published: 2025-10-24
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.21956v1

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$. Given the success of Transformers, improving their runtime during both training and inference is a popular research area. One such approach is the introduction of the linear attention (LA) mechanisms, which offers a linear time complexity of $O(ND^2)$ and have demonstrated comparable accuracy to regular attention. However, LA in practice lags behind its theoretical efficiency. We propose a novel method for LA's forward and backward passes, along with a highly-optimized CUDA implementation. Our approach outperforms the state-of-the-art by 3.3 times in speed and reduces memory consumption by 3.6 times. We validate these improvements in both single-layer and end-to-end settings by training a 1.4 billion parameter language model, which demonstrates similar expressivity to regular attention on major reasoning benchmarks.

---

### Model-Aware Tokenizer Transfer

Authors: Mykola Haltiuk, Aleksander Smywinski-Pohl
Published: 2025-10-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.21954v2

Large Language Models (LLMs) are trained to support an increasing number of languages, yet their predefined tokenizers remain a bottleneck for adapting models to lower-resource or distinct-script languages. Existing tokenizer transfer methods typically rely on semantic heuristics to initialize new embeddings, ignoring higher-layer model dynamics and limiting transfer quality. We propose Model-Aware Tokenizer Transfer (MATT), a method that incorporates model internals into the tokenizer transfer process. MATT introduces an Attention Influence Modeling (AIM) objective that distills inter-token communication patterns from a source model into a target model with a new tokenizer, providing an efficient warm-up before standard language modeling. Unlike approaches that focus solely on embedding similarity, MATT leverages attention behavior to guide embedding initialization and adaptation. Experiments across diverse linguistic settings show that MATT recovers a large fraction of the original model's performance within a few GPU hours, outperforming heuristic baselines. These results demonstrate that incorporating model-level signals offers a practical and effective path toward robust tokenizer transfer in multilingual LLMs.

---

### Revisiting Orbital Minimization Method for Neural Operator Decomposition

Authors: J. Jon Ryu, Samuel Zhou, Gregory W. Wornell
Published: 2025-10-24
Categories: cs.LG, math.NA, stat.ML
arXiv: https://arxiv.org/abs/2510.21952v1

Spectral decomposition of linear operators plays a central role in many areas of machine learning and scientific computing. Recent work has explored training neural networks to approximate eigenfunctions of such operators, enabling scalable approaches to representation learning, dynamical systems, and partial differential equations (PDEs). In this paper, we revisit a classical optimization framework from the computational physics literature known as the \emph{orbital minimization method} (OMM), originally proposed in the 1990s for solving eigenvalue problems in computational chemistry. We provide a simple linear-algebraic proof of the consistency of the OMM objective, and reveal connections between this method and several ideas that have appeared independently across different domains. Our primary goal is to justify its broader applicability in modern learning pipelines. We adapt this framework to train neural networks to decompose positive semidefinite operators, and demonstrate its practical advantages across a range of benchmark tasks. Our results highlight how revisiting classical numerical methods through the lens of modern theory and computation can provide not only a principled approach for deploying neural networks in numerical simulation, but also effective and scalable tools for machine learning.

---

### Generalization Bounds for Rank-sparse Neural Networks

Authors: Antoine Ledent, Rodrigo Alves, Yunwen Lei
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21945v3

It has been recently observed in much of the literature that neural networks exhibit a bottleneck rank property: for larger depths, the activation and weights of neural networks trained with gradient-based methods tend to be of approximately low rank. In fact, the rank of the activations of each layer converges to a fixed value referred to as the ``bottleneck rank'', which is the minimum rank required to represent the training data. This perspective is in line with the observation that regularizing linear networks (without activations) with weight decay is equivalent to minimizing the Schatten $p$ quasi norm of the neural network. In this paper we investigate the implications of this phenomenon for generalization. More specifically, we prove generalization bounds for neural networks which exploit the approximate low rank structure of the weight matrices if present. The final results rely on the Schatten $p$ quasi norms of the weight matrices: for small $p$, the bounds exhibit a sample complexity $ \widetilde{O}(WrL^2)$ where $W$ and $L$ are the width and depth of the neural network respectively and where $r$ is the rank of the weight matrices. As $p$ increases, the bound behaves more like a norm-based bound instead.

---

### Fixed Horizon Linear Quadratic Covariance Steering in Continuous Time with Hilbert-Schmidt Terminal Cost

Authors: Tushar Sial, Abhishek Halder
Published: 2025-10-24
Categories: math.OC, eess.SY, stat.ML
arXiv: https://arxiv.org/abs/2510.21944v2

We formulate and solve the fixed horizon linear quadratic covariance steering problem in continuous time with a terminal cost measured in Hilbert-Schmidt (i.e., Frobenius) norm error between the desired and the controlled terminal covariances. For this problem, the necessary conditions of optimality become a coupled matrix ODE two-point boundary value problem. To solve this system of equations, we design a matricial recursive algorithm and prove its convergence. The proposed algorithm and its analysis make use of the linear fractional transforms parameterized by the state transition matrix of the associated Hamiltonian matrix. To illustrate the results, we provide two numerical examples: one with a two dimensional and another with a six dimensional state space.

---

### AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testing

Authors: Samuel Bright-Thonney, Christina Reissel, Gaia Grosso, Nathaniel Woodward, Katya Govorkova, Andrzej Novak, Sang Eon Park, Eric Moreno, Philip Harris
Published: 2025-10-24
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2510.21935v2

Novelty detection in large scientific datasets faces two key challenges: the noisy and high-dimensional nature of experimental data, and the necessity of making statistically robust statements about any observed outliers. While there is a wealth of literature on anomaly detection via dimensionality reduction, most methods do not produce outputs compatible with quantifiable claims of scientific discovery. In this work we directly address these challenges, presenting the first step towards a unified pipeline for novelty detection adapted for the rigorous statistical demands of science. We introduce AutoSciDACT (Automated Scientific Discovery with Anomalous Contrastive Testing), a general-purpose pipeline for detecting novelty in scientific data. AutoSciDACT begins by creating expressive low-dimensional data representations using a contrastive pre-training, leveraging the abundance of high-quality simulated data in many scientific domains alongside expertise that can guide principled data augmentation strategies. These compact embeddings then enable an extremely sensitive machine learning-based two-sample test using the New Physics Learning Machine (NPLM) framework, which identifies and statistically quantifies deviations in observed data relative to a reference distribution (null hypothesis). We perform experiments across a range of astronomical, physical, biological, image, and synthetic datasets, demonstrating strong sensitivity to small injections of anomalous data across all domains.

---

### Joint Score-Threshold Optimization for Interpretable Risk Assessment

Authors: Fardin Ganjkhanloo, Emmett Springer, Erik H. Hoyer, Daniel L. Young, Kimia Ghobadi
Published: 2025-10-24
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.21934v3

Risk assessment tools in healthcare commonly employ point-based scoring systems that map patients to ordinal risk categories via thresholds. While electronic health record (EHR) data presents opportunities for data-driven optimization of these tools, two fundamental challenges impede standard supervised learning: (1) labels are often available only for extreme risk categories due to intervention-censored outcomes, and (2) misclassification cost is asymmetric and increases with ordinal distance. We propose a mixed-integer programming (MIP) framework that jointly optimizes scoring weights and category thresholds in the face of these challenges. Our approach prevents label-scarce category collapse via threshold constraints, and utilizes an asymmetric, distance-aware objective. The MIP framework supports governance constraints, including sign restrictions, sparsity, and minimal modifications to incumbent tools, ensuring practical deployability in clinical workflows. We further develop a continuous relaxation of the MIP problem to provide warm-start solutions for more efficient MIP optimization. We apply the proposed score optimization framework to a case study of inpatient falls risk assessment using the Johns Hopkins Fall Risk Assessment Tool.

---

### A Comparison of Conversational Models and Humans in Answering Technical Questions: the Firefox Case

Authors: Joao Correia, Daniel Coutinho, Marco Castelluccio, Caio Barbosa, Rafael de Mello, Anita Sarma, Alessandro Garcia, Marco Gerosa, Igor Steinmacher
Published: 2025-10-24
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.21933v1

The use of Large Language Models (LLMs) to support tasks in software development has steadily increased over recent years. From assisting developers in coding activities to providing conversational agents that answer newcomers' questions. In collaboration with the Mozilla Foundation, this study evaluates the effectiveness of Retrieval-Augmented Generation (RAG) in assisting developers within the Mozilla Firefox project. We conducted an empirical analysis comparing responses from human developers, a standard GPT model, and a GPT model enhanced with RAG, using real queries from Mozilla's developer chat rooms. To ensure a rigorous evaluation, Mozilla experts assessed the responses based on helpfulness, comprehensiveness, and conciseness. The results show that RAG-assisted responses were more comprehensive than human developers (62.50% to 54.17%) and almost as helpful (75.00% to 79.17%), suggesting RAG's potential to enhance developer assistance. However, the RAG responses were not as concise and often verbose. The results show the potential to apply RAG-based tools to Open Source Software (OSS) to minimize the load to core maintainers without losing answer quality. Toning down retrieval mechanisms and making responses even shorter in the future would enhance developer assistance in massive projects like Mozilla Firefox.

---

### Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks

Authors: Mahavir Dabas, Tran Huynh, Nikhil Reddy Billa, Jiachen T. Wang, Peng Gao, Charith Peris, Yao Ma, Rahul Gupta, Ming Jin, Prateek Mittal, Ruoxi Jia
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21910v3

Large language models remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Defending against novel jailbreaks represents a critical challenge in AI safety. Adversarial training -- designed to make models robust against worst-case perturbations -- has been the dominant paradigm for adversarial robustness. However, due to optimization challenges and difficulties in defining realistic threat models, adversarial training methods often fail on newly developed jailbreaks in practice. This paper proposes a new paradigm for improving robustness against unseen jailbreaks, centered on the Adversarial Déjà Vu hypothesis: novel jailbreaks are not fundamentally new, but largely recombinations of adversarial skills from previous attacks. We study this hypothesis through a large-scale analysis of 32 attack papers published over two years. Using an automated pipeline, we extract and compress adversarial skills into a sparse dictionary of primitives, with LLMs generating human-readable descriptions. Our analysis reveals that unseen attacks can be effectively explained as sparse compositions of earlier skills, with explanatory power increasing monotonically as skill coverage grows. Guided by this insight, we introduce Adversarial Skill Compositional Training (ASCoT), which trains on diverse compositions of skill primitives rather than isolated attack instances. ASCoT substantially improves robustness to unseen attacks, including multi-turn jailbreaks, while maintaining low over-refusal rates. We also demonstrate that expanding adversarial skill coverage, not just data scale, is key to defending against novel attacks. \textcolor{red}{\textbf{Warning: This paper contains content that may be harmful or offensive in nature.

---

### Explaining and Mitigating Crosslingual Tokenizer Inequities

Authors: Catherine Arnett, Tyler A. Chang, Stella Biderman, Benjamin K. Bergen
Published: 2025-10-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.21909v1

The number of tokens it takes to encode parallel text in different languages is known to vary. These disparities are called token premiums. Having high token premiums leads to less throughput during training and increases costs at inference. In this paper, we show that even after controlling for dataset size, vocabulary size, and data content, monolingual tokenizers exhibit a wide range of token premiums across languages. To understand the cross-linguistic differences that cause these token premiums, we train a suite of approximately 7,000 comparable monolingual tokenizers for 97 languages, manipulating tokenization algorithm, vocabulary size, and dataset size. We measure token premiums and test for a relationship between factors such as data similarity (between tokenizer training and evaluation), vocabulary size, and pre-tokenization. We also investigate the role of language-specific features such as writing system and word length. We find that similarity between training and test data does not impact token premiums, but vocabulary size and pre-tokenization do. While simply increasing vocabulary size does not lead to reduced token premium effects, we can determine an ``optimal'' vocabulary size for each language to achieve significantly reduced token premium effects. We also train superword tokenizers which allow merges over whitespaces, and we find that they both reduce token premium effects and improve compression overall. Thus, intervening on the vocabulary size or the pre-tokenizer significantly reduces crosslingual token premium effects.

---

### Enabling Robust In-Context Memory and Rapid Task Adaptation in Transformers with Hebbian and Gradient-Based Plasticity

Authors: Siddharth Chaudhary
Published: 2025-10-24
Categories: cs.NE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.21908v2

Large language models display in-context learning as an emergent effect of scale, but they rely on static weights during inference. In contrast, biological systems continually adapt via synaptic plasticity. We investigate whether explicit, biologically inspired plasticity can endow Transformers with faster in-sequence adaptation. To this end, we augment decoder-only Transformers with fast-weight modules updated either by (i) a neuromodulated Hebbian rule or (ii) the gradient-based plasticity mechanism of Duan et al. (2023). Across copying, regression, and few-shot classification tasks (CIFAR-FS, Omniglot), Hebbian plasticity consistently achieves lower loss and stronger few-shot generalization, while gradient-based updates perform best on long-horizon credit assignment. When associations are short and linearly separable, static weights suffice, defining a clear boundary condition for when plasticity helps. Analysis of learned modulatory signals reveals that gradient-based rules maintain large, persistent updates, whereas Hebbian plasticity is sharply gated around salient events. Together, these results show that explicit plasticity complements attention by enabling rapid, task-specific adaptation, and clarify when different plasticity mechanisms are most effective.

---

### Structure-Aware Cooperative Ensemble Evolutionary Optimization on Combinatorial Problems with Multimodal Large Language Models

Authors: Jie Zhao, Kang Hao Cheong
Published: 2025-10-24
Categories: cs.NE, cs.AI
arXiv: https://arxiv.org/abs/2510.21906v1

Evolutionary algorithms (EAs) have proven effective in exploring the vast solution spaces typical of graph-structured combinatorial problems. However, traditional encoding schemes, such as binary or numerical representations, often fail to straightforwardly capture the intricate structural properties of networks. Through employing the image-based encoding to preserve topological context, this study utilizes multimodal large language models (MLLMs) as evolutionary operators to facilitate structure-aware optimization over graph data. To address the visual clutter inherent in large-scale network visualizations, we leverage graph sparsification techniques to simplify structures while maintaining essential structural features. To further improve robustness and mitigate bias from different sparsification views, we propose a cooperative evolutionary optimization framework that facilitates cross-domain knowledge transfer and unifies multiple sparsified variants of diverse structures. Additionally, recognizing the sensitivity of MLLMs to network layout, we introduce an ensemble strategy that aggregates outputs from various layout configurations through consensus voting. Finally, experiments on real-world networks through various tasks demonstrate that our approach improves both the quality and reliability of solutions in MLLM-driven evolutionary optimization.

---

### TOM-SWE: User Mental Modeling For Software Engineering Agents

Authors: Xuhui Zhou, Valerie Chen, Zora Zhiruo Wang, Graham Neubig, Maarten Sap, Xingyao Wang
Published: 2025-10-24
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.21903v2

Recent advances in coding agents have made them capable of planning, editing, running, and testing complex code bases. Despite their growing ability in coding tasks, these systems still struggle to infer and track user intent, especially when instructions are underspecified or context-dependent. To bridge this gap, we introduce ToM-SWE, a dual-agent architecture that pairs a primary software-engineering (SWE) agent with a lightweight theory-of-mind (ToM) partner agent dedicated to modeling the user's mental state. The ToM agent infers user goals, constraints, and preferences from instructions and interaction history, maintains a \textbf{persistent memory} of the user, and provides user-related suggestions to the SWE agent. In two software engineering benchmarks (ambiguous SWE-bench and stateful SWE-bench), ToM-SWE improves task success rates and user satisfaction. Notably, on the stateful SWE benchmark, a newly introduced evaluation that provides agents with a user simulator along with previous interaction histories, ToM-SWE achieves a substantially higher task success rate of 59.7\% compared to 18.1\% for OpenHands, a state-of-the-art SWE agent. Furthermore, in a three-week study with professional developers using ToM-SWE in their daily work, participants found it useful 86\% of the time, underscoring the value of stateful user modeling for practical coding agents.

---

### Software Engineering Agents for Embodied Controller Generation : A Study in Minigrid Environments

Authors: Timothé Boulet, Xavier Hinaut, Clément Moulin-Frier
Published: 2025-10-24
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.21902v1

Software Engineering Agents (SWE-Agents) have proven effective for traditional software engineering tasks with accessible codebases, but their performance for embodied tasks requiring well-designed information discovery remains unexplored. We present the first extended evaluation of SWE-Agents on controller generation for embodied tasks, adapting Mini-SWE-Agent (MSWEA) to solve 20 diverse embodied tasks from the Minigrid environment. Our experiments compare agent performance across different information access conditions: with and without environment source code access, and with varying capabilities for interactive exploration. We quantify how different information access levels affect SWE-Agent performance for embodied tasks and analyze the relative importance of static code analysis versus dynamic exploration for task solving. This work establishes controller generation for embodied tasks as a crucial evaluation domain for SWE-Agents and provides baseline results for future research in efficient reasoning systems.

---

### Deep Literature Survey Automation with an Iterative Workflow

Authors: Hongbo Zhang, Han Cui, Yidong Wang, Yijian Tian, Qi Guo, Cunxiang Wang, Jian Wu, Chiyu Song, Yue Zhang
Published: 2025-10-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.21900v1

Automatic literature survey generation has attracted increasing attention, yet most existing systems follow a one-shot paradigm, where a large set of papers is retrieved at once and a static outline is generated before drafting. This design often leads to noisy retrieval, fragmented structures, and context overload, ultimately limiting survey quality. Inspired by the iterative reading process of human researchers, we propose \ours, a framework based on recurrent outline generation, in which a planning agent incrementally retrieves, reads, and updates the outline to ensure both exploration and coherence. To provide faithful paper-level grounding, we design paper cards that distill each paper into its contributions, methods, and findings, and introduce a review-and-refine loop with visualization enhancement to improve textual flow and integrate multimodal elements such as figures and tables. Experiments on both established and emerging topics show that \ours\ substantially outperforms state-of-the-art baselines in content coverage, structural coherence, and citation quality, while producing more accessible and better-organized surveys. To provide a more reliable assessment of such improvements, we further introduce Survey-Arena, a pairwise benchmark that complements absolute scoring and more clearly positions machine-generated surveys relative to human-written ones. The code is available at https://github.com/HancCui/IterSurvey\_Autosurveyv2.

---

### A supervised discriminant data representation: application to pattern classification

Authors: Fadi Dornaika, Ahmad Khoder, Abdelmalik Moujahid, Wassim Khoder
Published: 2025-10-24
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.21898v1

The performance of machine learning and pattern recognition algorithms generally depends on data representation. That is why, much of the current effort in performing machine learning algorithms goes into the design of preprocessing frameworks and data transformations able to support effective machine learning. The method proposed in this work consists of a hybrid linear feature extraction scheme to be used in supervised multi-class classification problems. Inspired by two recent linear discriminant methods: robust sparse linear discriminant analysis (RSLDA) and inter-class sparsitybased discriminative least square regression (ICS_DLSR), we propose a unifying criterion that is able to retain the advantages of these two powerful methods. The resulting transformation relies on sparsity-promoting techniques both to select the features that most accurately represent the data and to preserve the row-sparsity consistency property of samples from the same class. The linear transformation and the orthogonal matrix are estimated using an iterative alternating minimization scheme based on steepest descent gradient method and different initialization schemes. The proposed framework is generic in the sense that it allows the combination and tuning of other linear discriminant embedding methods. According to the experiments conducted on several datasets including faces, objects, and digits, the proposed method was able to outperform competing methods in most cases.

---

### Understanding Network Behaviors through Natural Language Question-Answering

Authors: Mingzhe Xing, Chang Tian, Jianan Zhang, Lichen Pan, Peipei Liu, Zhaoteng Yan, Yinliang Yue
Published: 2025-10-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.21894v1

Modern large-scale networks introduce significant complexity in understanding network behaviors, increasing the risk of misconfiguration. Prior work proposed to understand network behaviors by mining network configurations, typically relying on domain-specific languages interfaced with formal models. While effective, they suffer from a steep learning curve and limited flexibility. In contrast, natural language (NL) offers a more accessible and interpretable interface, motivating recent research on NL-guided network behavior understanding. Recent advances in large language models (LLMs) further enhance this direction, leveraging their extensive prior knowledge of network concepts and strong reasoning capabilities. However, three key challenges remain: 1) numerous router devices with lengthy configuration files challenge LLM's long-context understanding ability; 2) heterogeneity across devices and protocols impedes scalability; and 3) complex network topologies and protocols demand advanced reasoning abilities beyond the current capabilities of LLMs. To tackle the above challenges, we propose NetMind, a novel framework for querying networks using NL. Our approach introduces a tree-based configuration chunking strategy to preserve semantic coherence while enabling efficient partitioning. We then construct a unified fact graph as an intermediate representation to normalize vendor-specific configurations. Finally, we design a hybrid imperative-declarative language to reduce the reasoning burden on LLMs and enhance precision. We contribute a benchmark consisting of NL question-answer pairs paired with network configurations. Experiments demonstrate that NetMind achieves accurate and scalable network behavior understanding, outperforming existing baselines.

---

### Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation

Authors: Dhrupad Bhardwaj, Julia Kempe, Tim G. J. Rudner
Published: 2025-10-24
Categories: cs.CL, cs.AI, cs.LG, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.21891v2

To deploy large language models (LLMs) in high-stakes application domains that require substantively accurate responses to open-ended prompts, we need reliable, computationally inexpensive methods that assess the trustworthiness of long-form responses generated by LLMs. However, existing approaches often rely on claim-by-claim fact-checking, which is computationally expensive and brittle in long-form responses to open-ended prompts. In this work, we introduce semantic isotropy -- the degree of uniformity across normalized text embeddings on the unit sphere -- and use it to assess the trustworthiness of long-form responses generated by LLMs. To do so, we generate several long-form responses, embed them, and estimate the level of semantic isotropy of these responses as the angular dispersion of the embeddings on the unit sphere. We find that higher semantic isotropy -- that is, greater embedding dispersion -- reliably signals lower factual consistency across samples. Our approach requires no labeled data, no fine-tuning, and no hyperparameter selection, and can be used with open- or closed-weight embedding models. Across multiple domains, our method consistently outperforms existing aggregate trust signals in predicting nonfactuality using only a handful of samples, offering a practical, low-cost first-pass signal that complements claim-level verification in real-world LLM workflows.

---

### The Principles of Diffusion Models

Authors: Chieh-Hsin Lai, Yang Song, Dongjun Kim, Yuki Mitsufuji, Stefano Ermon
Published: 2025-10-24
Categories: cs.LG, cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2510.21890v3

This book presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse formulations arise from shared mathematical ideas. Diffusion modeling starts by defining a forward process that gradually corrupts data into noise, linking the data distribution to a simple prior through a continuum of intermediate distributions. The goal is to learn a reverse process that transforms noise back into data while recovering the same intermediates. We describe three complementary views. The variational view, inspired by variational autoencoders, sees diffusion as learning to remove noise step by step. The score-based view, rooted in energy-based modeling, learns the gradient of the evolving data distribution, indicating how to nudge samples toward more likely regions. The flow-based view, related to normalizing flows, treats generation as following a smooth path that moves samples from noise to data under a learned velocity field. These perspectives share a common backbone: a time-dependent velocity field whose flow transports a simple prior to the data. Sampling then amounts to solving a differential equation that evolves noise into data along a continuous trajectory. On this foundation, the book discusses guidance for controllable generation, efficient numerical solvers, and diffusion-motivated flow-map models that learn direct mappings between arbitrary times. It provides a conceptual and mathematically grounded understanding of diffusion models for readers with basic deep-learning knowledge. Supplementary materials for the book are available at the book website: https://the-principles-of-diffusion-models.github.io/

---

### Bridging Prediction and Attribution: Identifying Forward and Backward Causal Influence Ranges Using Assimilative Causal Inference

Authors: Marios Andreou, Nan Chen
Published: 2025-10-24
Categories: stat.ML, cs.LG, math.ST, physics.data-an, stat.ME
arXiv: https://arxiv.org/abs/2510.21889v2

Causal inference identifies cause-and-effect relationships between variables. While traditional approaches rely on data to reveal causal links, a recently developed method, assimilative causal inference (ACI), integrates observations with dynamical models. It utilizes Bayesian data assimilation to trace causes back from observed effects by quantifying the reduction in uncertainty. ACI advances the detection of instantaneous causal relationships and the intermittent reversal of causal roles over time. Beyond identifying causal connections, an equally important challenge is determining the associated causal influence range (CIR), indicating when causal influences emerged and for how long they persist. In this paper, ACI is employed to develop mathematically rigorous formulations of both forward and backward CIRs at each time. The forward CIR quantifies the temporal impact of a cause, while the backward CIR traces the onset of triggers for an observed effect, thus characterizing causal predictability and attribution of outcomes at each transient phase, respectively. Objective and robust metrics for both CIRs are introduced, eliminating the need for empirical thresholds. Computationally efficient approximation algorithms to compute CIRs are developed, which facilitate the use of closed-form expressions for a broad class of nonlinear dynamical systems. Numerical simulations demonstrate how this forward and backward CIR framework provides new possibilities for probing complex dynamical systems. It advances the study of bifurcation-driven and noise-induced tipping points in Earth systems, investigates the impact from resolving the interfering variables when determining the influence ranges, and elucidates atmospheric blocking mechanisms in the equatorial region. These results have direct implications for science, policy, and decision-making.

---

### Computational Hardness of Reinforcement Learning with Partial $q^π$-Realizability

Authors: Shayan Karimi, Xiaoqi Tan
Published: 2025-10-24
Categories: cs.AI, cs.CC, cs.LG
arXiv: https://arxiv.org/abs/2510.21888v1

This paper investigates the computational complexity of reinforcement learning in a novel linear function approximation regime, termed partial $q^π$-realizability. In this framework, the objective is to learn an $ε$-optimal policy with respect to a predefined policy set $Π$, under the assumption that all value functions for policies in $Π$ are linearly realizable. The assumptions of this framework are weaker than those in $q^π$-realizability but stronger than those in $q^*$-realizability, providing a practical model where function approximation naturally arises. We prove that learning an $ε$-optimal policy in this setting is computationally hard. Specifically, we establish NP-hardness under a parameterized greedy policy set (argmax) and show that - unless NP = RP - an exponential lower bound (in feature vector dimension) holds when the policy set contains softmax policies, under the Randomized Exponential Time Hypothesis. Our hardness results mirror those in $q^*$-realizability and suggest computational difficulty persists even when $Π$ is expanded beyond the optimal policy. To establish this, we reduce from two complexity problems, $δ$-Max-3SAT and $δ$-Max-3SAT(b), to instances of GLinear-$κ$-RL (greedy policy) and SLinear-$κ$-RL (softmax policy). Our findings indicate that positive computational results are generally unattainable in partial $q^π$-realizability, in contrast to $q^π$-realizability under a generative access model.

---

### Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions

Authors: Tobias Schmidt, Steffen Schneider, Matthias Bethge
Published: 2025-10-24
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.21706v1

We propose Equivariance by Contrast (EbC) to learn equivariant embeddings from observation pairs $(\mathbf{y}, g \cdot \mathbf{y})$, where $g$ is drawn from a finite group acting on the data. Our method jointly learns a latent space and a group representation in which group actions correspond to invertible linear maps -- without relying on group-specific inductive biases. We validate our approach on the infinite dSprites dataset with structured transformations defined by the finite group $G:= (R_m \times \mathbb{Z}_n \times \mathbb{Z}_n)$, combining discrete rotations and periodic translations. The resulting embeddings exhibit high-fidelity equivariance, with group operations faithfully reproduced in latent space. On synthetic data, we further validate the approach on the non-abelian orthogonal group $O(n)$ and the general linear group $GL(n)$. We also provide a theoretical proof for identifiability. While broad evaluation across diverse group types on real-world data remains future work, our results constitute the first successful demonstration of general-purpose encoder-only equivariant learning from group action observations alone, including non-trivial non-abelian groups and a product group motivated by modeling affine equivariances in computer vision.

---

### Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent

Authors: Christy Li, Josep Lopez Camuñas, Jake Thomas Touchet, Jacob Andreas, Agata Lapedriza, Antonio Torralba, Tamar Rott Shaham
Published: 2025-10-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21704v2

When a vision model performs image recognition, which visual attributes drive its predictions? Detecting unintended reliance on specific visual features is critical for ensuring model robustness, preventing overfitting, and avoiding spurious correlations. We introduce an automated framework for detecting such dependencies in trained vision models. At the core of our method is a self-reflective agent that systematically generates and tests hypotheses about visual attributes that a model may rely on. This process is iterative: the agent refines its hypotheses based on experimental outcomes and uses a self-evaluation protocol to assess whether its findings accurately explain model behavior. When inconsistencies arise, the agent self-reflects over its findings and triggers a new cycle of experimentation. We evaluate our approach on a novel benchmark of 130 models designed to exhibit diverse visual attribute dependencies across 18 categories. Our results show that the agent's performance consistently improves with self-reflection, with a significant performance increase over non-reflective baselines. We further demonstrate that the agent identifies real-world visual attribute dependencies in state-of-the-art models, including CLIP's vision encoder and the YOLOv8 object detector.

---

### Visual Diffusion Models are Geometric Solvers

Authors: Nir Goren, Shai Yehezkel, Omer Dahary, Andrey Voynov, Or Patashnik, Daniel Cohen-Or
Published: 2025-10-24
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.21697v2

In this paper we show that visual diffusion models can serve as effective geometric solvers: they can directly reason about geometric problems by working in pixel space. We first demonstrate this on the Inscribed Square Problem, a long-standing problem in geometry that asks whether every Jordan curve contains four points forming a square. We then extend the approach to two other well-known hard geometric problems: the Steiner Tree Problem and the Simple Polygon Problem. Our method treats each problem instance as an image and trains a standard visual diffusion model that transforms Gaussian noise into an image representing a valid approximate solution that closely matches the exact one. The model learns to transform noisy geometric structures into correct configurations, effectively recasting geometric reasoning as image generation. Unlike prior work that necessitates specialized architectures and domain-specific adaptations when applying diffusion to parametric geometric representations, we employ a standard visual diffusion model that operates on the visual representation of the problem. This simplicity highlights a surprising bridge between generative modeling and geometric problem solving. Beyond the specific problems studied here, our results point toward a broader paradigm: operating in image space provides a general and practical framework for approximating notoriously hard problems, and opens the door to tackling a far wider class of challenging geometric tasks.

---

### BachVid: Training-Free Video Generation with Consistent Background and Character

Authors: Han Yan, Xibin Song, Yifu Wang, Hongdong Li, Pan Ji, Chao Ma
Published: 2025-10-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21696v1

Diffusion Transformers (DiTs) have recently driven significant progress in text-to-video (T2V) generation. However, generating multiple videos with consistent characters and backgrounds remains a significant challenge. Existing methods typically rely on reference images or extensive training, and often only address character consistency, leaving background consistency to image-to-video models. We introduce BachVid, the first training-free method that achieves consistent video generation without needing any reference images. Our approach is based on a systematic analysis of DiT's attention mechanism and intermediate features, revealing its ability to extract foreground masks and identify matching points during the denoising process. Our method leverages this finding by first generating an identity video and caching the intermediate variables, and then inject these cached variables into corresponding positions in newly generated videos, ensuring both foreground and background consistency across multiple videos. Experimental results demonstrate that BachVid achieves robust consistency in generated videos without requiring additional training, offering a novel and efficient solution for consistent video generation without relying on reference images or additional training.

---

### A Knowledge-Graph Translation Layer for Mission-Aware Multi-Agent Path Planning in Spatiotemporal Dynamics

Authors: Edward Holmberg, Elias Ioup, Mahdi Abdelguerfi
Published: 2025-10-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.21695v1

The coordination of autonomous agents in dynamic environments is hampered by the semantic gap between high-level mission objectives and low-level planner inputs. To address this, we introduce a framework centered on a Knowledge Graph (KG) that functions as an intelligent translation layer. The KG's two-plane architecture compiles declarative facts into per-agent, mission-aware ``worldviews" and physics-aware traversal rules, decoupling mission semantics from a domain-agnostic planner. This allows complex, coordinated paths to be modified simply by changing facts in the KG. A case study involving Autonomous Underwater Vehicles (AUVs) in the Gulf of Mexico visually demonstrates the end-to-end process and quantitatively proves that different declarative policies produce distinct, high-performing outcomes. This work establishes the KG not merely as a data repository, but as a powerful, stateful orchestrator for creating adaptive and explainable autonomous systems.

---

### Mechanistic Interpretability for Neural TSP Solvers

Authors: Reuben Narad, Leonard Boussioux, Michael Wagner
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21693v1

Neural networks have advanced combinatorial optimization, with Transformer-based solvers achieving near-optimal solutions on the Traveling Salesman Problem (TSP) in milliseconds. However, these models operate as black boxes, providing no insight into the geometric patterns they learn or the heuristics they employ during tour construction. We address this opacity by applying sparse autoencoders (SAEs), a mechanistic interpretability technique, to a Transformer-based TSP solver, representing the first application of activation-based interpretability methods to operations research models. We train a pointer network with reinforcement learning on 100-node instances, then fit an SAE to the encoder's residual stream to discover an overcomplete dictionary of interpretable features. Our analysis reveals that the solver naturally develops features mirroring fundamental TSP concepts: boundary detectors that activate on convex-hull nodes, cluster-sensitive features responding to locally dense regions, and separator features encoding geometric partitions. These findings provide the first model-internal account of what neural TSP solvers compute before node selection, demonstrate that geometric structure emerges without explicit supervision, and suggest pathways toward transparent hybrid systems that combine neural efficiency with algorithmic interpretability. Interactive feature explorer: https://reubennarad.github.io/TSP_interp

---

### On Uncertainty Calibration for Equivariant Functions

Authors: Edward Berman, Jacob Ginesin, Marco Pacini, Robin Walters
Published: 2025-10-24
Categories: cs.LG, math.ST
arXiv: https://arxiv.org/abs/2510.21691v4

Data-sparse settings such as robotic manipulation, molecular physics, and galaxy morphology classification are some of the hardest domains for deep learning. For these problems, equivariant networks can help improve modeling across undersampled parts of the input space, and uncertainty estimation can guard against overconfidence. However, until now, the relationships between equivariance and model confidence, and more generally equivariance and model calibration, has yet to be studied. Since traditional classification and regression error terms show up in the definitions of calibration error, it is natural to suspect that previous work can be used to help understand the relationship between equivariance and calibration error. In this work, we present a theory relating equivariance to uncertainty estimation. By proving lower and upper bounds on uncertainty calibration errors (ECE and ENCE) under various equivariance conditions, we elucidate the generalization limits of equivariant models and illustrate how symmetry mismatch can result in miscalibration in both classification and regression. We complement our theoretical framework with numerical experiments that clarify the relationship between equivariance and uncertainty using a variety of real and simulated datasets, and we comment on trends with symmetry mismatch, group size, and aleatoric and epistemic uncertainties.

---

### On Thin Ice: Towards Explainable Conservation Monitoring via Attribution and Perturbations

Authors: Jiayi Zhou, Günel Aghakishiyeva, Saagar Arya, Julian Dale, James David Poling, Holly R. Houliston, Jamie N. Womble, Gregory D. Larsen, David W. Johnston, Brinnae Bent
Published: 2025-10-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.21689v1

Computer vision can accelerate ecological research and conservation monitoring, yet adoption in ecology lags in part because of a lack of trust in black-box neural-network-based models. We seek to address this challenge by applying post-hoc explanations to provide evidence for predictions and document limitations that are important to field deployment. Using aerial imagery from Glacier Bay National Park, we train a Faster R-CNN to detect pinnipeds (harbor seals) and generate explanations via gradient-based class activation mapping (HiResCAM, LayerCAM), local interpretable model-agnostic explanations (LIME), and perturbation-based explanations. We assess explanations along three axes relevant to field use: (i) localization fidelity: whether high-attribution regions coincide with the animal rather than background context; (ii) faithfulness: whether deletion/insertion tests produce changes in detector confidence; and (iii) diagnostic utility: whether explanations reveal systematic failure modes. Explanations concentrate on seal torsos and contours rather than surrounding ice/rock, and removal of the seals reduces detection confidence, providing model-evidence for true positives. The analysis also uncovers recurrent error sources, including confusion between seals and black ice and rocks. We translate these findings into actionable next steps for model development, including more targeted data curation and augmentation. By pairing object detection with post-hoc explainability, we can move beyond "black-box" predictions toward auditable, decision-supporting tools for conservation monitoring.

---

### Multimodal Datasets with Controllable Mutual Information

Authors: Raheem Karim Hashmani, Garrett W. Merz, Helen Qu, Mariel Pettee, Kyle Cranmer
Published: 2025-10-24
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.21686v2

We introduce a framework for generating highly multimodal datasets with explicitly calculable mutual information (MI) between modalities. This enables the construction of benchmark datasets that provide a novel testbed for systematic studies of mutual information estimators and multimodal self-supervised learning (SSL) techniques. Our framework constructs realistic datasets with known MI using a flow-based generative model and a structured causal framework for generating correlated latent variables. We benchmark a suite of MI estimators on datasets with varying ground truth MI values and verify that regression performance improves as the MI increases between input modalities and the target value. Finally, we describe how our framework can be applied to contexts including multi-detector astrophysics and SSL studies in the highly multimodal regime.

---

### WorldGrow: Generating Infinite 3D World

Authors: Sikuang Li, Chen Yang, Jiemin Fang, Taoran Yi, Jia Lu, Jiazhong Cen, Lingxi Xie, Wei Shen, Qi Tian
Published: 2025-10-24
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2510.21682v1

We tackle the challenge of generating the infinitely extendable 3D world -- large, continuous environments with coherent geometry and realistic appearance. Existing methods face key challenges: 2D-lifting approaches suffer from geometric and appearance inconsistencies across views, 3D implicit representations are hard to scale up, and current 3D foundation models are mostly object-centric, limiting their applicability to scene-level generation. Our key insight is leveraging strong generation priors from pre-trained 3D models for structured scene block generation. To this end, we propose WorldGrow, a hierarchical framework for unbounded 3D scene synthesis. Our method features three core components: (1) a data curation pipeline that extracts high-quality scene blocks for training, making the 3D structured latent representations suitable for scene generation; (2) a 3D block inpainting mechanism that enables context-aware scene extension; and (3) a coarse-to-fine generation strategy that ensures both global layout plausibility and local geometric/textural fidelity. Evaluated on the large-scale 3D-FRONT dataset, WorldGrow achieves SOTA performance in geometry reconstruction, while uniquely supporting infinite scene generation with photorealistic and structurally consistent outputs. These results highlight its capability for constructing large-scale virtual environments and potential for building future world models.

---

### A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing Detection

Authors: Gaku Morio, Harri Rowlands, Dominik Stammbach, Christopher D. Manning, Peter Henderson
Published: 2025-10-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.21679v1

Companies spend large amounts of money on public relations campaigns to project a positive brand image. However, sometimes there is a mismatch between what they say and what they do. Oil & gas companies, for example, are accused of "greenwashing" with imagery of climate-friendly initiatives. Understanding the framing, and changes in framing, at scale can help better understand the goals and nature of public relations campaigns. To address this, we introduce a benchmark dataset of expert-annotated video ads obtained from Facebook and YouTube. The dataset provides annotations for 13 framing types for more than 50 companies or advocacy groups across 20 countries. Our dataset is especially designed for the evaluation of vision-language models (VLMs), distinguishing it from past text-only framing datasets. Baseline experiments show some promising results, while leaving room for improvement for future work: GPT-4.1 can detect environmental messages with 79% F1 score, while our best model only achieves 46% F1 score on identifying framing around green innovation. We also identify challenges that VLMs must address, such as implicit framing, handling videos of various lengths, or implicit cultural backgrounds. Our dataset contributes to research in multimodal analysis of strategic communication in the energy sector.

---

### Optimal Graph Clustering without Edge Density Signals

Authors: Maximilien Dreveton, Elaine Siyu Liu, Matthias Grossglauser, Patrick Thiran
Published: 2025-10-24
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.21669v1

This paper establishes the theoretical limits of graph clustering under the Popularity-Adjusted Block Model (PABM), addressing limitations of existing models. In contrast to the Stochastic Block Model (SBM), which assumes uniform vertex degrees, and to the Degree-Corrected Block Model (DCBM), which applies uniform degree corrections across clusters, PABM introduces separate popularity parameters for intra- and inter-cluster connections. Our main contribution is the characterization of the optimal error rate for clustering under PABM, which provides novel insights on clustering hardness: we demonstrate that unlike SBM and DCBM, cluster recovery remains possible in PABM even when traditional edge-density signals vanish, provided intra- and inter-cluster popularity coefficients differ. This highlights a dimension of degree heterogeneity captured by PABM but overlooked by DCBM: local differences in connectivity patterns can enhance cluster separability independently of global edge densities. Finally, because PABM exhibits a richer structure, its expected adjacency matrix has rank between $k$ and $k^2$, where $k$ is the number of clusters. As a result, spectral embeddings based on the top $k$ eigenvectors may fail to capture important structural information. Our numerical experiments on both synthetic and real datasets confirm that spectral clustering algorithms incorporating $k^2$ eigenvectors outperform traditional spectral approaches.

---

### Foundation Models in Dermatopathology: Skin Tissue Classification

Authors: Riya Gupta, Yiwei Zong, Dennis H. Murphree
Published: 2025-10-24
Categories: cs.CV, q-bio.QM
arXiv: https://arxiv.org/abs/2510.21664v1

The rapid generation of whole-slide images (WSIs) in dermatopathology necessitates automated methods for efficient processing and accurate classification. This study evaluates the performance of two foundation models, UNI and Virchow2, as feature extractors for classifying WSIs into three diagnostic categories: melanocytic, basaloid, and squamous lesions. Patch-level embeddings were aggregated into slide-level features using a mean-aggregation strategy and subsequently used to train multiple machine learning classifiers, including logistic regression, gradient-boosted trees, and random forest models. Performance was assessed using precision, recall, true positive rate, false positive rate, and the area under the receiver operating characteristic curve (AUROC) on the test set. Results demonstrate that patch-level features extracted using Virchow2 outperformed those extracted via UNI across most slide-level classifiers, with logistic regression achieving the highest accuracy (90%) for Virchow2, though the difference was not statistically significant. The study also explored data augmentation techniques and image normalization to enhance model robustness and generalizability. The mean-aggregation approach provided reliable slide-level feature representations. All experimental results and metrics were tracked and visualized using WandB.ai, facilitating reproducibility and interpretability. This research highlights the potential of foundation models for automated WSI classification, providing a scalable and effective approach for dermatopathological diagnosis while paving the way for future advancements in slide-level representation learning.

---

### Self-Supervised Learning of Synapse Types from EM Images

Authors: Aarav Shetty, Gary B Huang
Published: 2025-10-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21663v1

Separating synapses into different classes based on their appearance in EM images has many applications in biology. Examples may include assigning a neurotransmitter to a particular class, or separating synapses whose strength can be modulated from those whose strength is fixed. Traditionally, this has been done in a supervised manner, giving the classification algorithm examples of the different classes. Here we instead separate synapses into classes based only on the observation that nearby synapses in the same neuron are likely more similar than synapses chosen randomly from different cells. We apply our methodology to data from {\it Drosophila}. Our approach has the advantage that the number of synapse types does not need to be known in advance. It may also provide a principled way to select ground-truth that spans the range of synapse structure.

---

### Long-tailed Species Recognition in the NACTI Wildlife Dataset

Authors: Zehua Liu, Tilo Burghardt
Published: 2025-10-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21657v1

As most ''in the wild'' data collections of the natural world, the North America Camera Trap Images (NACTI) dataset shows severe long-tailed class imbalance, noting that the largest 'Head' class alone covers >50% of the 3.7M images in the corpus. Building on the PyTorch Wildlife model, we present a systematic study of Long-Tail Recognition methodologies for species recognition on the NACTI dataset covering experiments on various LTR loss functions plus LTR-sensitive regularisation. Our best configuration achieves 99.40% Top-1 accuracy on our NACTI test data split, substantially improving over a 95.51% baseline using standard cross-entropy with Adam. This also improves on previously reported top performance in MLWIC2 at 96.8% albeit using partly unpublished (potentially different) partitioning, optimiser, and evaluation protocols. To evaluate domain shifts (e.g. night-time captures, occlusion, motion-blur) towards other datasets we construct a Reduced-Bias Test set from the ENA-Detection dataset where our experimentally optimised long-tail enhanced model achieves leading 52.55% accuracy (up from 51.20% with WCE loss), demonstrating stronger generalisation capabilities under distribution shift. We document the consistent improvements of LTR-enhancing scheduler choices in this NACTI wildlife domain, particularly when in tandem with state-of-the-art LTR losses. We finally discuss qualitative and quantitative shortcomings that LTR methods cannot sufficiently address, including catastrophic breakdown for 'Tail' classes under severe domain shift. For maximum reproducibility we publish all dataset splits, key code, and full network weights.

---

### CMOMgen: Complex Multi-Ontology Alignment via Pattern-Guided In-Context Learning

Authors: Marta Contreiras Silva, Daniel Faria, Catia Pesquita
Published: 2025-10-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.21656v1

Constructing comprehensive knowledge graphs requires the use of multiple ontologies in order to fully contextualize data into a domain. Ontology matching finds equivalences between concepts interconnecting ontologies and creating a cohesive semantic layer. While the simple pairwise state of the art is well established, simple equivalence mappings cannot provide full semantic integration of related but disjoint ontologies. Complex multi-ontology matching (CMOM) aligns one source entity to composite logical expressions of multiple target entities, establishing more nuanced equivalences and provenance along the ontological hierarchy. We present CMOMgen, the first end-to-end CMOM strategy that generates complete and semantically sound mappings, without establishing any restrictions on the number of target ontologies or entities. Retrieval-Augmented Generation selects relevant classes to compose the mapping and filters matching reference mappings to serve as examples, enhancing In-Context Learning. The strategy was evaluated in three biomedical tasks with partial reference alignments. CMOMgen outperforms baselines in class selection, demonstrating the impact of having a dedicated strategy. Our strategy also achieves a minimum of 63% in F1-score, outperforming all baselines and ablated versions in two out of three tasks and placing second in the third. Furthermore, a manual evaluation of non-reference mappings showed that 46% of the mappings achieve the maximum score, further substantiating its ability to construct semantically sound mappings.

---

### Group Inertial Poser: Multi-Person Pose and Global Translation from Sparse Inertial Sensors and Ultra-Wideband Ranging

Authors: Ying Xue, Jiaxi Jiang, Rayan Armani, Dominik Hollidt, Yi-Chi Liao, Christian Holz
Published: 2025-10-24
Categories: cs.CV, cs.AI, cs.GR, cs.HC
arXiv: https://arxiv.org/abs/2510.21654v1

Tracking human full-body motion using sparse wearable inertial measurement units (IMUs) overcomes the limitations of occlusion and instrumentation of the environment inherent in vision-based approaches. However, purely IMU-based tracking compromises translation estimates and accurate relative positioning between individuals, as inertial cues are inherently self-referential and provide no direct spatial reference for others. In this paper, we present a novel approach for robustly estimating body poses and global translation for multiple individuals by leveraging the distances between sparse wearable sensors - both on each individual and across multiple individuals. Our method Group Inertial Poser estimates these absolute distances between pairs of sensors from ultra-wideband ranging (UWB) and fuses them with inertial observations as input into structured state-space models to integrate temporal motion patterns for precise 3D pose estimation. Our novel two-step optimization further leverages the estimated distances for accurately tracking people's global trajectories through the world. We also introduce GIP-DB, the first IMU+UWB dataset for two-person tracking, which comprises 200 minutes of motion recordings from 14 participants. In our evaluation, Group Inertial Poser outperforms previous state-of-the-art methods in accuracy and robustness across synthetic and real-world data, showing the promise of IMU+UWB-based multi-human motion capture in the wild. Code, models, dataset: https://github.com/eth-siplab/GroupInertialPoser

---

### AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite

Authors: Jonathan Bragg, Mike D'Arcy, Nishant Balepur, Dan Bareket, Bhavana Dalvi, Sergey Feldman, Dany Haddad, Jena D. Hwang, Peter Jansen, Varsha Kishore, Bodhisattwa Prasad Majumder, Aakanksha Naik et al.
Published: 2025-10-24
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.21652v2

AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging from general-purpose "deep research" systems to specialized science-specific agents, such as AI Scientist and AIGS. Rigorous evaluation of these agents is critical for progress. Yet existing benchmarks fall short on several fronts: they often (1) lack reproducible agent tools necessary for a controlled comparison of core agentic capabilities; (2) do not account for confounding variables such as model cost and tool access; (3) do not provide standardized interfaces for quick agent prototyping and evaluation; (4) fail to provide holistic, product-informed measures of real-world use cases such as science research; and (5) lack comprehensive baseline agents necessary to identify true advances. In response, we define principles and tooling for more rigorously benchmarking agents. Using these, we present AstaBench, a suite that provides a holistic measure of agentic ability to perform scientific research, comprising 2400+ problems spanning the entire scientific discovery process and multiple scientific domains, and including many problems inspired by actual user requests to deployed Asta agents. Our suite comes with the first scientific research environment with production-grade search tools that enable controlled, reproducible evaluation, better accounting for confounders. Alongside, we provide a comprehensive suite of nine science-optimized classes of Asta agents and numerous baselines. Our extensive evaluation of 57 agents across 22 agent classes reveals several interesting findings, most importantly that despite meaningful progress on certain individual aspects, AI remains far from solving the challenge of science research assistance.

---

### A Dynamic Knowledge Distillation Method Based on the Gompertz Curve

Authors: Han Yang, Guangjun Qin
Published: 2025-10-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.21649v1

This paper introduces a novel dynamic knowledge distillation framework, Gompertz-CNN, which integrates the Gompertz growth model into the training process to address the limitations of traditional knowledge distillation. Conventional methods often fail to capture the evolving cognitive capacity of student models, leading to suboptimal knowledge transfer. To overcome this, we propose a stage-aware distillation strategy that dynamically adjusts the weight of distillation loss based on the Gompertz curve, reflecting the student's learning progression: slow initial growth, rapid mid-phase improvement, and late-stage saturation. Our framework incorporates Wasserstein distance to measure feature-level discrepancies and gradient matching to align backward propagation behaviors between teacher and student models. These components are unified under a multi-loss objective, where the Gompertz curve modulates the influence of distillation losses over time. Extensive experiments on CIFAR-10 and CIFAR-100 using various teacher-student architectures (e.g., ResNet50 and MobileNet_v2) demonstrate that Gompertz-CNN consistently outperforms traditional distillation methods, achieving up to 8% and 4% accuracy gains on CIFAR-10 and CIFAR-100, respectively.

---

### Hybrid Genetic Algorithm for Optimal User Order Routing: Multi-Objective Solver Optimization in CoW Protocol Batch Auctions

Authors: Mitchell Marfinetz
Published: 2025-10-24
Categories: cs.NE
arXiv: https://arxiv.org/abs/2510.21647v1

CoW Protocol batch auctions aggregate user intents and rely on solvers to find optimal execution paths that maximize user surplus across heterogeneous automated market makers (AMMs) under stringent auction deadlines. Deterministic single-objective heuristics that optimize only expected output frequently fail to exploit split-flow opportunities across multiple parallel paths and to internalize gas, slippage, and execution risk constraints in a unified search. We apply evolutionary multi-objective optimization to this blockchain routing problem, proposing a hybrid genetic algorithm (GA) architecture for real-time solver optimization that combines a production-grade, multi-objective NSGA-II engine with adaptive instance profiling and deterministic baselines. Our core engine encodes variable-length path sets with continuous split ratios and evolves candidate route-and-volume allocations under a Pareto objective vector F = (user surplus, -gas, -slippage, -risk), enabling principled trade-offs and anytime operation within the auction deadline. An adaptive controller selects between GA and a deterministic dual-decomposition optimizer with Bellman-Ford based negative-cycle detection, with a guarantee to never underperform the baseline. The open-source system integrates six protection layers and passes 8/8 tests, validating safety and correctness. In a 14-stratum benchmark (30 seeds each), the hybrid approach yields absolute user-surplus gains of approximately 0.40-9.82 ETH on small-to-medium orders, while large high-fragmentation orders are unprofitable across gas regimes. Convergence occurs in about 0.5 s median (soft capped at 1.0 s) within a 2-second limit. We are not aware of an openly documented multi-objective GA with end-to-end safety for real-time DEX routing.

---